{"id":"https://openalex.org/W2962761044","doi":"https://doi.org/10.48550/arxiv.1705.07819","title":"Regularizing deep networks using efficient layerwise adversarial training","display_name":"Regularizing deep networks using efficient layerwise adversarial training","publication_year":2017,"publication_date":"2017-05-22","ids":{"openalex":"https://openalex.org/W2962761044","doi":"https://doi.org/10.48550/arxiv.1705.07819","mag":"2962761044"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1705.07819","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.07819","pdf_url":"https://arxiv.org/pdf/1705.07819","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1705.07819","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081528888","display_name":"Swami Sankaranarayanan","orcid":"https://orcid.org/0000-0002-9239-3221","observed_orcids":["https://orcid.org/0000-0002-9239-3221"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sankaranarayanan, Swami","raw_affiliation_strings":["University of Maryland College Park , MD","University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland College Park , MD","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086355248","display_name":"Arpit Jain","orcid":"https://orcid.org/0000-0002-3158-7305","observed_orcids":["https://orcid.org/0000-0002-3158-7305"]},"institutions":[{"id":"https://openalex.org/I1332737386","display_name":"General Electric (United States)","ror":"https://ror.org/013msgt25","country_code":"US","type":"company","lineage":["https://openalex.org/I1332737386"]},{"id":"https://openalex.org/I4210134512","display_name":"GE Global Research (United States)","ror":"https://ror.org/03e06qt98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134512"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jain, Arpit","raw_affiliation_strings":["GE Global Research Niskayuna , NY","GE Global Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE Global Research Niskayuna , NY","institution_ids":["https://openalex.org/I4210134512"]},{"raw_affiliation_string":"GE Global Research","institution_ids":["https://openalex.org/I1332737386","https://openalex.org/I4210134512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102762707","display_name":"Rama Chellappa","orcid":"https://orcid.org/0000-0002-7638-1650","observed_orcids":["https://orcid.org/0000-0002-7638-1650"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chellappa, Rama","raw_affiliation_strings":["University of Maryland College Park , MD","University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland College Park , MD","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113875926","display_name":"Ser Nam Lim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134512","display_name":"GE Global Research (United States)","ror":"https://ror.org/03e06qt98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134512"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lim, Ser Nam","raw_affiliation_strings":["Avitas Systems, GE Global Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avitas Systems, GE Global Research","institution_ids":["https://openalex.org/I4210134512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":84,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0017999999690800905,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.9850000143051147},{"id":"https://openalex.org/keywords/neural-network-regularization","display_name":"neural network regularization","score":0.6769999861717224},{"id":"https://openalex.org/keywords/adversarial-robustness","display_name":"adversarial robustness","score":0.8870000243186951},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.6790000200271606},{"id":"https://openalex.org/keywords/wide-resnet","display_name":"WideResNet","score":0.7609999775886536},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.7390000224113464}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9026126861572266},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.8798497319221497},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.740692138671875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229088544845581},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6927453279495239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6679350137710571},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6158351302146912},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5245996713638306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44246146082878113},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1705.07819","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.07819","pdf_url":"https://arxiv.org/pdf/1705.07819","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/11688","doi":null,"is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/11688","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/11688/11547","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.1705.07819","doi":"https://doi.org/10.48550/arxiv.1705.07819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1705.07819","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1705.07819","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1705.07819","pdf_url":"https://arxiv.org/pdf/1705.07819","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4383626004","display_name":null,"funder_award_id":"2014-14071600012","funder_id":"https://openalex.org/F4320312530","funder_display_name":"Office of the Director of National Intelligence"},{"id":"https://openalex.org/G73875660","display_name":null,"funder_award_id":"2014-14071600012","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"}],"funders":[{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962761044.pdf","grobid_xml":"https://content.openalex.org/works/W2962761044.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1569098853","https://openalex.org/W1673923490","https://openalex.org/W1678450113","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1883420340","https://openalex.org/W1945616565","https://openalex.org/W2095705004","https://openalex.org/W2096733369","https://openalex.org/W2163605009","https://openalex.org/W2174868984","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2218318129","https://openalex.org/W2342045095","https://openalex.org/W2508156266","https://openalex.org/W2556096924","https://openalex.org/W2558950531","https://openalex.org/W2584667682","https://openalex.org/W2964137095","https://openalex.org/W2964159205","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3089485619","https://openalex.org/W3119111712","https://openalex.org/W2963566318","https://openalex.org/W3014936620","https://openalex.org/W3135151133","https://openalex.org/W3143848010","https://openalex.org/W3166792421","https://openalex.org/W4407450965","https://openalex.org/W3092171228","https://openalex.org/W4362672614"],"abstract_inverted_index":{"Adversarial":[0],"training":[1,46,118],"has":[2,30],"been":[3,32],"shown":[4],"to":[5,12,16,43,68,99],"regularize":[6],"deep":[7,24,71],"neural":[8],"networks":[9,29],"in":[10,79,131],"addition":[11],"increasing":[13],"their":[14],"robustness":[15],"adversarial":[17,45,83,117],"examples.":[18],"However,":[19],"its":[20],"impact":[21],"on":[22,82,106,122],"very":[23,70],"state":[25],"of":[26,56,93,114,145],"the":[27,54,91,102,112,115],"art":[28],"not":[31],"fully":[33],"investigated.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"present":[39],"an":[40],"efficient":[41],"approach":[42,127],"perform":[44],"by":[47],"perturbing":[48,94,100],"intermediate":[49,95],"layer":[50,96],"activations":[51,97],"and":[52,76,84,108,141],"study":[53],"use":[55,65],"such":[57,73],"perturbations":[58,67],"as":[59,74],"a":[60,135],"regularizer":[61],"during":[62],"training.":[63],"We":[64],"these":[66],"train":[69],"models":[72,144],"ResNets":[75],"show":[77,111,124],"improvement":[78,130],"performance":[80],"both":[81],"original":[85],"test":[86],"data.":[87],"Our":[88],"experiments":[89],"highlight":[90],"benefits":[92],"compared":[98],"only":[101],"inputs.":[103],"The":[104],"results":[105,121],"CIFAR-10":[107],"CIFAR-100":[109],"datasets":[110],"merits":[113],"proposed":[116],"approach.":[119],"Additional":[120],"WideResNets":[123],"that":[125],"our":[126],"provides":[128],"significant":[129],"classification":[132],"accuracy":[133],"for":[134],"given":[136],"base":[137,143],"model,":[138],"outperforming":[139],"dropout":[140],"other":[142],"larger":[146],"size.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":7}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-07-30T00:00:00"}